#safety
1 resource and 1 guide tagged #safety on ChangeGamer. Includes Guardrails and Safety Filters for Agents.
- Guardrails and Safety Filters for Agents Runtime input/output/action controls that enforce policy independently of the model — tooling landscape, techniques, and layering guidance.
Guides
- Voice Agent Guardrails: Checking What the Agent Says Before the Caller Hears It Voice agent guardrails for spoken output: sentence-level gating before TTS, fail-closed judges, spoken numbers a text PII filter misses, readback before state changes, transcription-driven injection, refusal phrasing for the ear, and an adversarial test list.